Aria Khoshsirat
DISI, Polo Ferrari – Povo 1, Via Sommarive, 9, 38123 Povo, Trento, Italy
Aria Khoshsirat is a Postdoctoral Researcher at the Department of Information Engineering and Computer Science, University of Trento, working under the supervision of Prof. Paolo Rech. He received his Ph.D. in Information Engineering from the University of Padova in 2025 as a Marie Skłodowska-Curie Fellow within the Greenedge Innovative Training Network (ITN). His doctoral research focused on energy-efficient edge computing, with particular emphasis on energy measurement, profiling and optimization techniques for machine learning workloads on resource-constrained edge devices.
During his Ph.D., he was a Visiting Researcher at Imperial College London, where he worked on resource-efficient task partitioning and parallel execution of deep learning models across edge devices.
He also joined Toshiba Research Europe in Bristol as an R&D Researcher, contributing to research on large language model fine-tuning and personalized AI deployment in decentralized edge networks.
His research interests include edge AI, distributed and decentralized machine learning, energy-efficient computing, computer vision, large language models, and reliable machine learning systems. His work combines empirical system measurements with algorithmic and systems-level optimization to improve the efficiency of AI applications deployed on edge platforms.